1. Wiera: Towards Flexible Multi-Tiered Geo-Distributed Cloud Storage Instances
Zhe Zhang

2. CAP Theorem For distributed system, “P” is an imperative property
Tradeoff between “A” and “C”

3. Cost Model in AWS Cloud providers use cost model to charge customers
There exists a tradeoff between cost and speed

4. Agenda Introduction Dynamic Consistency Dynamic Primary Locations
Reducing cost with Multi-tier storage
Exploiting Remote Storage Tiers
Conclusions

5. Agenda Introduction Dynamic Consistency Dynamic Primary Locations
Reducing cost with Multi-tier storage
Exploiting Remote Storage Tiers
Conclusions

6. Wiera Architecture Wiera User Interface: coordination
Global Policy Manager: user-defined policies
Tiera Server Manager: mange Tiera instances

7. Agenda Introduction Dynamic Consistency Dynamic Primary Locations
Reducing cost with Multi-tier storage
Exploiting Remote Storage Tiers
Conclusions

8. Strong Consistency and Weak Availability
put a C c
User a sends put request

9. Strong Consistency and Weak Availability
lock B b A
put a C c
User a sends put request
Get a global lock

10. Strong Consistency and Weak Availability
lock B b A
put a C c
User a sends put request
Get a global lock
Synchronously updating the object in B and C

11. Strong Consistency and Weak Availability
response a C c
User a sends put request
Get a global lock
Synchronously updating the object in B and C
Release the lock and response to user

12. Strong Consistency and Weak Availability
get b A
get a C
get c
User a sends put request
Get a global lock
Synchronously updating the object in B and C
Release the lock and response to user
Users start reading from all replications

13. Weak Consistency and Strong Availability
put a C c
User a sends put request

14. Weak Consistency and Strong Availability
put a
response C c
User a sends put request
User a immediately gets response

15. Weak Consistency and Strong Availability
get b A
outdated object
get a C
get c
User a sends put request
User a immediately gets response
Users start reading the object but b, c get outdated version of the object

16. Weak Consistency and Strong Availability
get
update b A
get a C
get c
update
User a sends put request
User a immediately gets response
Users start reading the object but b, c get outdated version of the object
Updates eventually propagate to B and C

17. Weak Consistency and Strong Availability
get b A
get a C
get c
User a sends put request
User a immediately gets response
Users start reading the object but b, c get outdated version of the object
Updates eventually propagate to B and C
Users read consistent object

18. Medium Consistency and Availability
put a C c
User a get response after all servers receive the object

19. Medium Consistency and Availability
get b A
get a C
get c
User a get response after all servers receive the object
All get requests are forwarded to A

20. Wiera Solution A tradeoff between latency and consistency
Dynamically switch consistency models
MultiPrimaries
PrimaryBackup
EventualConsistency
High Latency
Strong Consistency
Medium Latency
Medium Consistency
Low Latency
Weak Consistency

21. Dynamic Consistency
Reducing latency once MultiplePrimaries goes beyond threshold
Recovering consistency when latency meet the requirement

22. Agenda Introduction Dynamic Consistency Dynamic Primary Locations
Reducing cost with Multi-tier storage
Exploiting Remote Storage Tiers
Conclusions

23. Imbalanced Traffic on Primary Locations
get
get
USA
Asia
Primary
forwared get

24. Imbalanced Traffic on Primary Locations
get
get
USA
Asia
Primary
forwared get

25. Imbalanced Traffic on Primary Locations
get
get
USA
Asia
forwared get
Primary

26. Changing Primary
Maintain good consistency
Reduce latency

27. Agenda Introduction Dynamic Consistency Dynamic Primary Locations
Reducing cost with Multi-tier storage
Exploiting Remote Storage Tiers
Conclusions

28. Motivation Data popularity follows Zipfian distribution
Only a small portion of data are considered as hot data
Cold data are rarely accessed
Using different storage media for different popularity
Hot data need fast access speed
Cold data can tolerate low access speed

29. Tradeoff between Cost and Latency
Expensive but Fast
Tier1(EBS with SSD)
Tier2(EBS with HHD)
Tier3(S3)
Tier4(S3-IA)
Cheap but Slow

30. Reducing Cost Using Multi-tier Storage
Performance of accessing local tier storage
Performance of accessing centralized cold storage

31. Reducing Cost Using Multi-tier Storage
Performance of accessing local tier storage
Money Saver!
10TB can save $300
Performance of accessing centralized cold storage

32. Agenda Introduction Dynamic Consistency Dynamic Primary Locations
Reducing cost with Multi-tier storage
Exploiting Remote Storage Tiers
Conclusions

33. Test Setup
get
get
Azure
AWS
Primary
Backup
forwared get
Create an Wiera instance on Azure as PrimaryBackupConsistency

34. Exploiting Remote Storage Tiers
Azure VM
Azure
Azure Disk
AWS VM
Amzon
Azure Memory
Amazon AWS
Azure

35. Conclusions Wiera is a robust geo-distributed cloud storage
Wiera dynamically change configurations to meet desired metrics:
Latency
Consistency
Cost
Criticism:
When exploiting remote storage tiers, the author did not try to create PrimaryBackup instance on AWS

36. Questions ?